网易有道EmotiVoice

By admin, 29 十一月, 2023

EmotiVoice is a powerful and modern open-source text-to-speech engine. EmotiVoice speaks both English and Chinese, and with over 2000 different voices (refer to the List of Voices for details). The most prominent feature is emotional synthesis, allowing you to create speech with a wide range of emotions, including happy, excited, sad, angry and others.

https://github.com/netease-youdao/EmotiVoice

docker版本占用内存大概3.2G,响应速度非常快。以合成“我挥一挥衣袖,不带走一片云彩”为例,8核CPU需要1.5秒。coqui占用内容大概1.3G,合成同样句子需要大概8.5秒。

如果使用非docker的版本,占用内存1G,合成上面的句子只需要0.6秒,可完美替代Coqui。

启动docker后可以查询conatiner_id:

sudo docker ps


然后进入docker系统:

sudo docker exec -it f2f5831fabd6 /bin/bash


下面命令何以启动demo网页服务:

streamlit run demo_page.py

Packaging code:

pyinstaller --copy-metadata tqdm --copy-metadata regex --copy-metadata requests --copy-metadata packaging --copy-metadata filelock --copy-metadata numpy --copy-metadata tokenizers --copy-metadata torch --hidden-import config server.py

 

 

标签

评论

Restricted HTML

  • 允许的HTML标签:<a href hreflang> <em> <strong> <cite> <blockquote cite> <code> <ul type> <ol start type> <li> <dl> <dt> <dd> <h2 id> <h3 id> <h4 id> <h5 id> <h6 id> <img src>
  • 自动断行和分段。
  • 网页和电子邮件地址自动转换为链接。
验证码
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
请输入"Drupal10"